| --- |
| license: other |
| tags: |
| - heal |
| - horizon |
| --- |
| |
| # InternVL2.5-2B |
|
|
| **Original model repository:** [OpenGVLab/InternVL2_5-2B](https://huggingface.co/OpenGVLab/InternVL2_5-2B) |
|
|
| ## Model Introduction |
|
|
| InternVL2.5-2B is an instruction-tuned Vision-Language Model (VLM) built on the InternVL2.5 architecture. It combines an InternViT-300M vision encoder, an MLP projector, and InternLM2.5-Chat-1.8B as its language model. It is designed for visual question answering, OCR, document and chart understanding, visual grounding, image description, and general multimodal dialogue. |
|
|
| ## Deployment Metrics |
|
|
| ### Model Parameters |
|
|
| | Metric | Value | |
| |---|---:| |
| | Total model parameters | 2.206B | |
| | Vision model (ViT) parameters | 316.6M | |
| | Language model (LM) parameters | 1.889B | |
|
|
| Parameter counts are calculated from the tensors stored in the upstream checkpoint. |
|
|
| ### Performance Metrics |
|
|
| | Chips | Data Type | ViT Image Size | Sequence Length (tokens) | Maximum Context Length (tokens) | BPU Cores (ViT / Prefill / Decode) | ViT Latency (ms) | TTFT (ms) | Prefill TPS (token/s) | Decode TPS (token/s) | BPU Memory (GB) | CPU Memory (GB) | |
| |---|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:| |
| | J6P | W8A8 | 448 × 448 | 512 | 1024 | 4 / 4 / 4 | 41.984 | 82.650 | 14,105.694 | 71.620 | 2.4 | 0.79 | |
|
|
| > **Note:** TTFT includes preprocessing and ViT latency. Memory values represent the peak memory usage measured during the specified performance test. |
|
|
